SOTAVerified

Point Cloud Segmentation

3D point cloud segmentation is the process of classifying point clouds into multiple homogeneous regions, the points in the same region will have the same properties. The segmentation is challenging because of high redundancy, uneven sampling density, and lack explicit structure of point cloud data. This problem has many applications in robotics such as intelligent vehicles, autonomous mapping and navigation.

Source: 3D point cloud segmentation: A survey

Papers

Showing 1120 of 272 papers

TitleStatusHype
Point Transformer V2: Grouped Vector Attention and Partition-based PoolingCode2
FEC: Fast Euclidean Clustering for Point Cloud SegmentationCode2
Stratified Transformer for 3D Point Cloud SegmentationCode2
Masked Autoencoders for Point Cloud Self-supervised LearningCode2
Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP FrameworkCode2
OpenMaskDINO3D : Reasoning 3D Segmentation via Large Language ModelCode1
Lidar Panoptic Segmentation in an Open WorldCode1
Towards Modality-agnostic Label-efficient Segmentation with Entropy-Regularized Distribution AlignmentCode1
HGL: Hierarchical Geometry Learning for Test-time Adaptation in 3D Point Cloud SegmentationCode1
Dual-level Adaptive Self-Labeling for Novel Class Discovery in Point Cloud SegmentationCode1
Show:102550
← PrevPage 2 of 28Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1OcCo-PCNmean Corruption Error (mCE)1.17Unverified
2OcCo-PointNetmean Corruption Error (mCE)1.13Unverified
3PointNet++mean Corruption Error (mCE)1.11Unverified
4PointTransformersmean Corruption Error (mCE)1.05Unverified
5PointMLPmean Corruption Error (mCE)0.98Unverified
6PointMAEmean Corruption Error (mCE)0.93Unverified
7GDANetmean Corruption Error (mCE)0.92Unverified
8GDANetmean Corruption Error (mCE)0.89Unverified